플러그인

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

A browser that lives in the DSH host: every session gets its own tab, the AI drives it, and you watch or take over that same tab inside the DSH Web UI — logins, 2FA, QR codes and CAPTCHAs included.

Turn approved tracker tickets into review-ready pull requests with DeepSeek Harness.

Windows computer-use plugin for AI agents with reusable window targets, UI Automation, window-bound screenshots, background-first verified input, isolated Chromium automation, MCP, CLI, and installable skills.

Community DeepSeek Harness plugin: deterministic engineering orchestration with Commander, Executor and Smart Watchdog (CxService + cx_controller tool).

Deterministic engineering orchestration for DeepSeek Harness with Commander, Executor, Smart Watchdog, bounded recovery and durable execution state.

智能体选择器：像模型选择器一样在输入框旁勾选委派目标+具体模型，把对话任务派给外部智能体（Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code）执行，结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。

Browser automation for DeepSeek Harness: agent-driven real-browser control (managed Chrome with an isolated persistent profile, or attach to your daily Chrome over CDP) with snapshot, click, fill and page-reading tools; records manual operation flows and replays them with variable slots to create test data on demand; ships 27 browser_* tools plus a Settings panel.

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.

Computer use plugin for DeepSeek Harness: one plugin composing the computer seam, a Playwright provider, and the computer_* tools

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

All-in-one UI enhancement layer for DeepSeek Harness web: prompt library with quick-insert and management, two-step AI polish, predicted-reply dock with click-to-send, MCP tool management, scheduled automation, smart session titles, adjustable chat width, full-width AI messages without gray background, auto-collapse for long user messages with smooth expand/collapse animations, and scene-specific entrance animations across all plugin surfaces.

Vision browser tool: drives real Chrome over CDP with browser-use and reads the page with deepseek-v4-flash-vision-exp, so canvas text, text baked into images and values in rendered charts are readable; returns JSON validated against a caller-supplied schema and reports per-run token cost.

Durable heartbeat and cron automations for DeepSeek Harness

Run live iOS simulators and your real iPhone over USB inside DeepSeek Harness conversations with 22 agent tools, MJPEG previews, and SwiftUI hot reload.

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.

Firefox browser control for DeepSeek Harness: token-authenticated WebSocket bridge + text-first browser_* tools driving the user's own Firefox via the companion AMO extension

Linux crontab-style scheduled tasks for DeepSeek Harness: the LLM can schedule recurring workflow runs and prompt-driven tasks with cron expressions, plus proactive task suggestions inferred from the chat.

One-click Claude Code and Codex hooks for DeepSeek Harness: auto-discovers your existing hooks config and runs it on the official bridge plugins.

Schedules workspace Agent runs in fresh Result Sessions with persistent audit history, using a stock DSH Conversation tab or a global Shell page when its slots are available.

macOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut, Photoshop, WPS, native clients) like a human — 14 tools for mouse, keyboard, scrolling, app activation, windows and screenshots, plus a vision closed-loop (desktop_see for image understanding + desktop_locate for UI element coordinates) that reuses dsh existing vision credentials. GUI-session service starts on demand, no login autostart.